Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/dshakes/compassWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/dshakes/compass/onboard)<a href="https://agentmods.dev/commands/dshakes/compass/onboard"><img src="https://agentmods.dev/badge/commands/dshakes/compass/onboard/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/dshakes/compass/onboard"><img src="https://agentmods.dev/badge/commands/dshakes/compass/onboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00033 | $0.00891 |
| Opus 5.5 | $0.00013 | $0.00356 |
| Sonnet 5.5 | $0.00007 | $0.00178 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
onboard scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboard me into this repo${ARGUMENTS:+ at $ARGUMENTS}.
Work through these steps in order. Use cheap subagents aggressively — Haiku for any mechanical run (installs, test execution, grepping), Sonnet for reasoning and writing. Ask before anything destructive; never push, merge, or deploy.
1 · Detect the stack
Scan the repo root for indicator files and print a one-line summary:
go.mod→ Go (note Go version)package.json→ Node; checkpnpm-lock.yaml/yarn.lock/package-lock.jsonfor the package managerCargo.toml→ Rust (note edition / MSRV from the manifest)pyproject.tomlorrequirements.txt→ Python; preferuvif availablemix.exs→ Elixir;Gemfile→ Ruby- Multiple files → polyglot; list all
2 · Install dependencies
Run the appropriate install command for each detected stack. Delegate this to a Haiku subagent — it's pure mechanics. Skip gracefully if deps are already present (cache hit / lockfile unchanged).
| Stack | Command |
|---|---|
| Go | go mod download |
| Node/npm | npm install |
| Node/pnpm | pnpm install |
| Node/yarn | yarn install |
| Rust | cargo fetch |
| Python (uv) | uv sync |
| Python (pip) | pip install -r requirements.txt or pip install -e . |
| Elixir | mix deps.get |
| Ruby | bundle install |
3 · Build + test
Find the correct commands — check Makefile targets, README, package.json scripts,
go.mod, Cargo.toml, pyproject.toml. Run them via a Haiku subagent.
Report PASS or FAIL with the last ~10 lines of output.
Do NOT fix failing tests now — just surface them.
Typical probes (in order):
make build && make test(if a Makefile with those targets exists)- Stack-native:
go build ./... && go test ./.../cargo test/npm test/pytest -q - Any
scripts.testentry inpackage.json
4 · Write or refresh CLAUDE.md
Invoke the bootstrap-agent-config skill — it inspects the repo and produces a
grounded CLAUDE.md (build command, test command, run command, key directories,
conventions). If the skill isn't available, do it yourself:
- Read existing
CLAUDE.md(if any); update only stale sections. - Ground every claim in code you actually read — no hallucinated commands.
- Keep it short: a dense page beats five vague ones.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 84 lines · 33 tokens per session scan A dd529a9919e4
onboard is a command published in the GitHub repository dshakes/compass (21 stars, last pushed 4d ago), licensed MIT. It adds 33 tokens to every session and 891 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
onboard compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| onboarddshakes/compass | Command | 21 | 4d ago | MIT | A | 33 | Claude Code |
| awesome-chatgpttaishi-i/awesome-ChatGPT-repositories | Command | 3.4k | yesterday | CC0-1.0 | A | 0 | Claude Code |
| initfrankchu91/mindbase-llm-wiki | Command | 136 | 21d ago | MIT | A | 28 | Claude Code |
| commitechoVic/blade-code | Command | 181 | 24d ago | MIT | A | 8 | Claude Code |
| propsmill/infrahub-mcp | Command | 10 | yesterday | Apache-2.0 | A | 18 | Claude Code |
| recallnaimkatiman/continuous-improvement | Command | 9 | 5d ago | MIT | A | 44 | Claude Code |
| claude-requestverivus-oss/llm-cli-gateway | Command | 16 | 3d ago | MIT | A | 14 | Claude Code |